{"id":"W4402916113","doi":"10.1109/cvprw63382.2024.00211","title":"VMCML: Video and Music Matching via Cross-Modality Lifting","year":2024,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Modality (human–computer interaction); Computer science; Matching (statistics); Computer vision; Artificial intelligence; Speech recognition; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004322749,0.0001026904,0.00009926901,0.00005145011,0.0002152228,0.001518655,0.0002740417,0.00003967222,0.00006479441],"category_scores_gemma":[0.00001692643,0.00008296762,0.00003346833,0.0002545375,0.00004473178,0.001017965,0.0003380046,0.0001373441,0.00005381802],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573441,"about_ca_system_score_gemma":0.00004570909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008789111,"about_ca_topic_score_gemma":0.00000904573,"domain_scores_codex":[0.9990208,0.00001942006,0.000168887,0.0004097735,0.0001602085,0.0002209193],"domain_scores_gemma":[0.9995726,0.00009121795,0.00002608773,0.000213627,0.00002443549,0.00007199877],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001571078,0.00001706576,0.001475784,0.0004096013,0.00002063802,0.00007113532,0.005146155,0.00007345007,0.007207393,0.09863674,0.001448341,0.8854921],"study_design_scores_gemma":[0.0003316102,0.00004200786,0.01279118,0.0006004995,0.00001464303,0.0002309014,0.0001078081,0.6452847,0.009199969,0.3118242,0.01875854,0.0008139916],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1711683,0.0005404628,0.815153,0.001812641,0.0003880109,0.00003747054,3.053821e-7,0.0004633075,0.01043654],"genre_scores_gemma":[0.9601316,0.000004029425,0.03707676,0.001766091,0.0001584985,0.000002696337,3.418602e-7,0.000008162529,0.0008518224],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8846781,"threshold_uncertainty_score":0.9995179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01991925318231961,"score_gpt":0.2848456987159592,"score_spread":0.2649264455336395,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}